Improve the state-of-the-art in image registration for cardiac images by developing machine-learning techniques, with a specific

通过开发机器学习技术，提高心脏图像图像配准的最先进水平，并具有特定的

• 批准号: 2274702
• 金额: --
• 依托单位: University of Sheffield
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2019
• 资助国家: 英国
• 起止时间: 2019 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2274702
• 关键词: Improve; state; art; image; registration

Cardiovascular diseases are one of the leading causes of deaths in the UK. Registration of cardiac images is an important preprocessing step for many diagnostic tools that identify these diseases. Manual image registration takes valuable time which medical professionals could instead use more productively. An automatic solution to registration would free up limited resources, increasing the efficiency of the NHS. The aim of this research is to develop an automatic or semi-automatic system to carry out this process, utilizing modern deep learning techniques

心血管疾病是英国死亡的主要原因之一。心脏图像的配准是识别这些疾病的许多诊断工具的重要预处理步骤。手动图像配准需要宝贵的时间，而医疗专业人员可以更有效地利用这些时间。自动登记的解决方案将释放有限的资源，提高NHS的效率。这项研究的目的是开发一个自动或半自动系统来执行这一过程，利用现代深度学习技术